Network-aware Data Prefetching Optimization of Computations in a Heterogeneous HPC Framework - Publication - Bridge of Knowledge

Search

Network-aware Data Prefetching Optimization of Computations in a Heterogeneous HPC Framework

Abstract

Rapid development of diverse computer architectures and hardware accelerators caused that designing parallel systems faces new problems resulting from their heterogeneity. Our implementation of a parallel system called KernelHive allows to efficiently run applications in a heterogeneous environment consisting of multiple collections of nodes with different types of computing devices. The execution engine of the system is open for optimizer implementations, focusing on various criteria. In this paper, we proposea new optimizer for KernelHive, that utilizes distributed databases and performs data prefetching to optimize the execution time of applications, which process large input data. Employing a versatile data management scheme, which allows combining various distributed data providers, we propose using NoSQL databases for our purposes. We support our solution with results of experiments with real executions of our OpenCL implementation of a regular expression matching application in various hardware configurations. Additionally, we propose a network-aware scheduling scheme for selecting hardware for the proposed optimizer and present simulations that demonstrate its advantages.

Citations

  • 1

    CrossRef

  • 0

    Web of Science

  • 0

    Scopus

Keywords

Details

Category:
Articles
Type:
artykuły w czasopismach recenzowanych i innych wydawnictwach ciągłych
Published in:
International Journal of Computer Networks & Communications (IJCNC) no. 6, edition 5, pages 85 - 98,
ISSN: 0975-2293
Language:
English
Publication year:
2014
Bibliographic description:
Rościszewski P.: Network-aware Data Prefetching Optimization of Computations in a Heterogeneous HPC Framework// International Journal of Computer Networks & Communications (IJCNC). -Vol. 6., iss. 5 (2014), s.85-98
DOI:
Digital Object Identifier (open in new tab) 10.5121/ijcnc.2014.6506
Verified by:
Gdańsk University of Technology

seen 114 times

Recommended for you

Meta Tags